# Ensembles of GANs for synthetic training data generation

arXiv: https://arxiv.org/abs/2104.11797 · HTML: https://mlsanity.com/paper/2104.11797/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 32 references that are in the map.
- First posted on arXiv 23 Apr 2021.

## Builds on (most cited first, 21 of 21)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [Spectral Normalization for Generative Adversarial Networks](https://mlsanity.com/paper/1802.05957/) (2018)
- [Self-Attention Generative Adversarial Networks](https://mlsanity.com/paper/1805.08318/) (2018)
- [GAN-based Synthetic Medical Image Augmentation for increased CNN Performance in Liver Lesion Classification](https://mlsanity.com/paper/1803.01229/) (2018)
- [Pros and Cons of GAN Evaluation Measures](https://mlsanity.com/paper/1802.03446/) (2018)
- [VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learning](https://mlsanity.com/paper/1705.07761/) (2017)
- [Medical Image Synthesis for Data Augmentation and Anonymization using Generative Adversarial Networks](https://mlsanity.com/paper/1807.10225/) (2018)
- [GAN Augmentation: Augmenting Training Data using Generative Adversarial Networks](https://mlsanity.com/paper/1810.10863/) (2018)
- [PacGAN: The power of two samples in generative adversarial networks](https://mlsanity.com/paper/1712.04086/) (2017)
- [How good is my GAN?](https://mlsanity.com/paper/1807.09499/) (2018)
- [Diverse Image Generation via Self-Conditioned GANs](https://mlsanity.com/paper/2006.10728/) (2020)
- [AdaGAN: Boosting Generative Models](https://mlsanity.com/paper/1701.02386/) (2017)
- [Synthetic Medical Images from Dual Generative Adversarial Networks](https://mlsanity.com/paper/1709.01872/) (2017)
- [Boosted Generative Models](https://mlsanity.com/paper/1702.08484/) (2017)
- [Generating Artificial Data for Private Deep Learning](https://mlsanity.com/paper/1803.03148/) (2018)
- [Ensembles of Generative Adversarial Networks](https://mlsanity.com/paper/1612.00991/) (2016)

## Built on by (most cited first, 6 of 6)

- [Beware of diffusion models for synthesizing medical images -- A comparison with GANs in terms of memorizing brain MRI and chest x-ray images](https://mlsanity.com/paper/2305.07644/) (2023)
- [Brain tumor segmentation using synthetic MR images -- A comparison of GANs and diffusion models](https://mlsanity.com/paper/2306.02986/) (2023)
- [Rethinking Surgical Instrument Segmentation: A Background Image Can Be All You Need](https://mlsanity.com/paper/2206.11804/) (2022)
- [Synthetic Data for Model Selection](https://mlsanity.com/paper/2105.00717/) (2021)
- [Does an ensemble of GANs lead to better performance when training segmentation networks with synthetic images?](https://mlsanity.com/paper/2211.04086/) (2022)
- [Beyond a Single Mode: GAN Ensembles for Diverse Medical Data Generation](https://mlsanity.com/paper/2503.24258/) (2025)

## Abstract (arXiv)

Insufficient training data is a major bottleneck for most deep learning practices, not least in medical imaging where data is difficult to collect and publicly available datasets are scarce due to ethics and privacy. This work investigates the use of synthetic images, created by generative adversarial networks (GANs), as the only source of training data. We demonstrate that for this application, it is of great importance to make use of multiple GANs to improve the diversity of the generated data, i.e. to sufficiently cover the data distribution. While a single GAN can generate seemingly diverse image content, training on this data in most cases lead to severe over-fitting. We test the impact of ensembled GANs on synthetic 2D data as well as common image datasets (SVHN and CIFAR-10), and using both DCGANs and progressively growing GANs. As a specific use case, we focus on synthesizing digital pathology patches to provide anonymized training data.